{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T02:13:48Z","timestamp":1784772828482,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T00:00:00Z","timestamp":1602460800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"State Key Development Program","award":["2016YFB1001004"],"award-info":[{"award-number":["2016YFB1001004"]}]},{"name":"Guangdong Basic and Applied Basic Research Foundation","award":["2020B1515020048"],"award-info":[{"award-number":["2020B1515020048"]}]},{"name":"National Natural Science Foundation of China","award":["61976250"],"award-info":[{"award-number":["61976250"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,12]]},"DOI":"10.1145\/3394171.3413862","type":"proceedings-article","created":{"date-parts":[[2020,10,12]],"date-time":"2020-10-12T13:10:44Z","timestamp":1602508244000},"page":"1283-1291","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":52,"title":["Reinforcement Learning for Weakly Supervised Temporal Grounding of Natural Language in Untrimmed Videos"],"prefix":"10.1145","author":[{"given":"Jie","family":"Wu","sequence":"first","affiliation":[{"name":"Sun Yat-sen University, guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoguang","family":"Han","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University & DarkMatter AI, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,10,12]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1015"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018199"},{"key":"e_1_3_2_2_4_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence.","author":"Chen Tianshui","year":"2018"},{"key":"e_1_3_2_2_5_1","unstructured":"Junyoung Chung Caglar Gulcehre KyungHyun Cho and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014).  Junyoung Chung Caglar Gulcehre KyungHyun Cho and Yoshua Bengio. 2014. Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv:1412.3555 (2014)."},{"key":"e_1_3_2_2_6_1","unstructured":"Xuguang Duan Wenbing Huang Chuang Gan Jingdong Wang Wenwu Zhu and Junzhou Huang. 2018. Weakly supervised dense event captioning in videos. In Advances in Neural Information Processing Systems. 3059--3069.  Xuguang Duan Wenbing Huang Chuang Gan Jingdong Wang Wenwu Zhu and Junzhou Huang. 2018. Weakly supervised dense event captioning in videos. In Advances in Neural Information Processing Systems. 3059--3069."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_4"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"e_1_3_2_2_9_1","volume-title":"WSLLN: Weakly Supervised Natural Language Localization Networks.","author":"Gao Mingfei","year":"2019"},{"key":"e_1_3_2_2_10_1","volume-title":"MAC: Mining Activity Concepts for Language-based Temporal Localization. In IEEE Winter Conference on Applications of Computer Vision. IEEE, 245--253","author":"Ge Runzhou","year":"2019"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"e_1_3_2_2_13_1","unstructured":"Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105.  Alex Krizhevsky Ilya Sutskever and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems. 1097--1105."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12308"},{"key":"e_1_3_2_2_15_1","unstructured":"Zhijie Lin Zhou Zhao Zhu Zhang Qi Wang and Huasheng Liu. 2020. Weakly-Supervised Video Moment Retrieval via Semantic Completion Network. (2020).  Zhijie Lin Zhou Zhao Zhu Zhang Qi Wang and Huasheng Liu. 2020. Weakly-Supervised Video Moment Retrieval via Semantic Completion Network. (2020)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210003"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240549"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351074"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"crossref","unstructured":"Minh-Thang Luong Hieu Pham and Christopher D Manning. 2015. Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015).  Minh-Thang Luong Hieu Pham and Christopher D Manning. 2015. Effective approaches to attention-based neural machine translation. arXiv preprint arXiv:1508.04025 (2015).","DOI":"10.18653\/v1\/D15-1166"},{"key":"e_1_3_2_2_20_1","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 11592--11601","author":"Mithun Niluthpol Chowdhury"},{"key":"e_1_3_2_2_21_1","volume-title":"International conference on machine learning. 1928--1937","author":"Mnih Volodymyr","year":"2016"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_35"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"e_1_3_2_2_24_1","unstructured":"Marc'Aurelio Ranzato Sumit Chopra Michael Auli and Wojciech Zaremba. 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015).  Marc'Aurelio Ranzato Sumit Chopra Michael Auli and Wojciech Zaremba. 2015. Sequence level training with recurrent neural networks. arXiv preprint arXiv:1511.06732 (2015)."},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"crossref","unstructured":"Yukai Shi Guanbin Li Qingxing Cao Keze Wang and Liang Lin. 2019. Face hallucination by attentive sequence optimization with reinforcement learning. IEEE transactions on pattern analysis and machine intelligence (2019).  Yukai Shi Guanbin Li Qingxing Cao Keze Wang and Liang Lin. 2019. Face hallucination by attentive sequence optimization with reinforcement learning. IEEE transactions on pattern analysis and machine intelligence (2019).","DOI":"10.1109\/TPAMI.2019.2915301"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"e_1_3_2_2_28_1","unstructured":"Nitish Srivastava Geoffrey Hinton Alex Krizhevsky Ilya Sutskever and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research Vol. 15 1 (2014) 1929--1958.  Nitish Srivastava Geoffrey Hinton Alex Krizhevsky Ilya Sutskever and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research Vol. 15 1 (2014) 1929--1958."},{"key":"e_1_3_2_2_29_1","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press.  Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"crossref","unstructured":"Jiajie Wang Jiangchao Yao Ya Zhang and Rui Zhang. 2018. Collaborative learning for weakly supervised object detection. arXiv preprint arXiv:1802.03531 (2018).  Jiajie Wang Jiangchao Yao Ya Zhang and Rui Zhang. 2018. Collaborative learning for weakly supervised object detection. arXiv preprint arXiv:1802.03531 (2018).","DOI":"10.24963\/ijcai.2018\/135"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00042"},{"key":"e_1_3_2_2_34_1","volume-title":"Reinforcement Learning","author":"Williams Ronald J"},{"key":"e_1_3_2_2_35_1","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence.","author":"Wu Jie","year":"2020"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019062"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00427"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350935"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019159"},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00134"},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350879"}],"event":{"name":"MM '20: The 28th ACM International Conference on Multimedia","location":"Seattle WA USA","acronym":"MM '20","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 28th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413862","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3394171.3413862","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:01:18Z","timestamp":1750197678000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3394171.3413862"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,12]]},"references-count":44,"alternative-id":["10.1145\/3394171.3413862","10.1145\/3394171"],"URL":"https:\/\/doi.org\/10.1145\/3394171.3413862","relation":{},"subject":[],"published":{"date-parts":[[2020,10,12]]},"assertion":[{"value":"2020-10-12","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}